Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis Adjusted Langevin Algorithm - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Statistics and Computing Année : 2014

Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis Adjusted Langevin Algorithm

Résumé

In this paper, we establish explicit convergence rates for Markov chains in Wasserstein distance. Compared to the more classical total variation bounds, the proposed rate of convergence leads to useful insights for the analysis of MCMC algorithms, and suggests ways to construct sampler with good mixing rate even if the dimension of the underlying sampling space is large. We illustrate these results by analyzing the Exponential Integrator version of the Metropolis Adjusted Langevin Algorithm. We illustrate our findings using a Bayesian linear inverse problem.
Fichier non déposé

Dates et versions

hal-01745697 , version 1 (28-03-2018)

Identifiants

Citer

Alain Durmus, Éric Moulines. Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis Adjusted Langevin Algorithm. Statistics and Computing, 2014, 25, pp.5-19. ⟨10.1007/s11222-014-9511-z⟩. ⟨hal-01745697⟩
92 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More